Proceeding of the Faculty of technical Sciences, Novi Sad

Electrotechnical and Computer Engineering

Vol. 40 No. 07 (2025): Proceedings of the Faculty of Technical Sciences

TAXI TRIP TRAVEL TIME AND FARE PREDICTION

  • Natalija Krsmanović
DOI:
https://doi.org/10.24867/31BE23Krsmanovic
Submitted
July 9, 2025
Published
2026-01-02

Abstract

The paper presents the process of creating a system for analysing and processing data on taxi rides in New York. Two datasets were utilized – one containing data on taxi rides and the other containing weather data. Preprocessing was performed on these data sets to create the final dataset for model training. Different machine learning algorithms were employed to predict duration and price. Several experiments were conducted, and the results are compared to those from the literature.

References

  1. [1] C. Antoniades, Delara Fadavi, Antoine Foba Amon, “Fare and Duration Prediction: A Study of New York City Taxi Ride”, Semantic Scholar, 43844792, 2016.
  2. [2] Huang, H., Pouls, M., Meyer, A., Pauly, M, “ Travel Time Prediction Using Tree-Based Ensembles”, Lecture Notes in Computer Science, vol 12433, pp 412–427, 2020.
  3. [3] Poongodi M, Malviya M, Kumar C, “New York City taxi trip duration prediction using MLP and XGBoost”, International Journal of System Assurance Engineering and Management, 13(Suppl 1), 16-27, 2022.
  4. [4] https://www.nyc.gov/site/tlc/about/tlc-trip-recorddata.page (pristupljeno u avgustu 2024.)
  5. [5] https://www.kaggle.com/datasets/selfishgene/historic al-hourly-weather-data/code (pristupljeno u avgustu 2024.)
  6. [6] https://machinelearningmastery.com/why-one-hotencode-data-in-machine-learning/ (pristupljeno u avgustu 2024.)
  7. [7] https://github.com/jahnavi-chowdary/New-York-TaxiFare-Prediction/tree/master (pristupljeno u septembru 2024.)
  8. [8] https://github.com/raymonduchen/MLND-P6-NewYork-City-Taxi-Fare-Prection/tree/master (pristupljeno u septembru 2024.)